Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    limitation of warranty, liability, or kind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prioridad
    0.89
    𝐆
    0.88
     carreras
    0.86
     Ху
    0.85
    ᡤ
    0.85
     sueño
    0.85
    𝐠
    0.85
    㴦
    0.83
    ول
    0.81
    渟
    0.81
    POSITIVE LOGITS
    ,
    1.15
     ,
    1.04
     any
    0.86
     किसी
    0.85
    ↵↵
    0.85
     a
    0.83
     कोई
    0.83
    ↵↵↵
    0.82
     किंवा
    0.81
    ,\
    0.80
    Act Density 0.001%

    No Known Activations